- Home
- Skills
- Finance & Accounting
- bank fee analyzer
Works with the AI Agents you already use
bank fee analyzer
Extract, group, and analyze bank fees and financial identifiers from account statements via MCP.
Free
bank fee analyzer
Example session with this skill installed
Analyze these transaction details and find the fees: { "date": "2024-05-01", "description": "International Wire Transfer", "amount": 1000, "fee": 25 }. Also verify the IBAN.
- Read your context and instructions
- Compiled the bank fee analyzer
The analysis identified a $25.00 international wire transfer fee. The transaction has been validated.
Summary
- Total Fees: $25.00
- Category: Service Charges
- Status: Validated tax and IBAN details.
Connects securely to your tools. The creator never sees your data.
About this skill
The problem
Manually auditing bank statements for hidden fees and grouped costs is slow and prone to human error. Developers and finance teams need a predictable way to parse transaction data and isolate service charges without building custom regex patterns for every bank.
What it does
- Identifies and extracts bank fees from raw account movement objects.
- Groups fees by concept to provide a structured overview of banking costs.
- Validates tax details, VAT numbers, and IBANs within the financial context.
- Returns standardized JSON responses for easy integration into accounting or auditing pipelines.
Frameworks & tools
Requires an MCP server hosting the bank_fee_analyzer tool. Works with any LLM environment supporting Model Context Protocol (MCP) like Claude Desktop or Cursor.
Why this beats prompting it yourself
General-purpose LLMs often hallucinate or miscalculate financial figures when processing raw statements. This skill enforces a strict data schema, handles offline validation without network latency, and ensures consistent error codes instead of unpredictable conversational failures.
Use cases
- Automate monthly bank fee audits for corporate accounts.
- Verify client IBAN and tax details before generating invoices.
- Vet new vendors by validating VAT and tax registration data.
- Extract hidden service charges from exported bank CSV or JSON data.
Known limitations
The tool is stateless and does not remember context between calls. It requires properly formatted account statement objects to function correctly.
Find more skills like this on the Claude Skills Marketplace, the Codex Skills Marketplace and the Gemini Skills Marketplace, or browse Claude Skills for Finance & Accounting.
Stateless operation requiring full context per call. Requires data to be structured as account statement objects. Does not support raw PDF or image OCR directly.
How to use
- 1
Connect your agent to the Agensi MCP
Copy the prompt and paste it into Claude, ChatGPT, Cursor or any agent that supports MCP. It sets up the connection for you. Manual setup
- 2
Sign in to Agensi
Your agent shows a sign-in link. Sign in and click Allow.
- 3
Ask for what you need
Your agent loads this skill and uses it on your task. It always asks before buying a skill.
Reviews
No reviews yet
Be one of the first to try it. Every listed skill goes through the trust checks below.
Security scanned
Checked by our 8-point scan before listing
3 uses
Times used to date
Free to use
No account required to browse
Trust & safety
Security scan
Security scan passed 3 months ago
- Free with an Agensi account
Permissions
No special permissions declared or detected